Diagnosing LLM Arbitration Behavior over Pre-e — leaderboard
Metric: Margin (self-reported). Source: benchmarklist.com. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 | 23.5 |
| 2 | Phi-4 | -0.4 |
| 3 | Qwen 3 32B | -11.5 |
| 4 | Mistral 7B | -19 |
| 5 | GPT-4o Mini | -52.1 |
| 6 | Llama 3 8B | -66.1 |
Interactive version: theaggregate.ai/benchmark?slug=diagnosing-llm-arbitration-behavior-over-pre-e · How the rankings work · Data refreshed daily, snapshot 2026-07-22.